Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4364 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.3845. Min Act: -0.0001

Data Index: 1615363 (Python Code)

Max Activating Token Index: 801

Text #1

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.2370. Min Act: -0.0001

Data Index: 1444058 (Python Code)

Max Activating Token Index: 291

Text #2

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0461. Min Act: -0.0000

Data Index: 1506378 (Python Code)

Max Activating Token Index: 420

Text #3

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.1107. Min Act: -0.0000

Data Index: 1508321 (Python Code)

Max Activating Token Index: 879

Text #4

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0963. Min Act: -0.0000

Data Index: 1367283 (Python Code)

Max Activating Token Index: 327

Text #5

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0304. Min Act: -0.0001

Data Index: 1568004 (Python Code)

Max Activating Token Index: 185

Text #6

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1567515 (Python Code)

Max Activating Token Index: 963

Text #7

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1446055 (Python Code)

Max Activating Token Index: 170

Text #8

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9439. Min Act: -0.0001

Data Index: 1616312 (Python Code)

Max Activating Token Index: 936

Text #9

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9197. Min Act: -0.0000

Data Index: 1370056 (Python Code)

Max Activating Token Index: 777

Text #10

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1369126 (Python Code)

Max Activating Token Index: 787

Text #11

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1593986 (Python Code)

Max Activating Token Index: 715

Text #12

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9769. Min Act: -0.0000

Data Index: 1384880 (Python Code)

Max Activating Token Index: 382

Text #13

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9870. Min Act: -0.0001

Data Index: 1589656 (Python Code)

Max Activating Token Index: 157

Text #14

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9766. Min Act: -0.0000

Data Index: 1542443 (Python Code)

Max Activating Token Index: 703

Text #15

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1427388 (Python Code)

Max Activating Token Index: 733

Text #16

Max Range: 1.3845. Min Range: -1.3845

Max Act: 1.0000. Min Act: -0.0001

Data Index: 1457441 (Python Code)

Max Activating Token Index: 394

Text #17

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1624493 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.8921. Min Act: -0.0001

Data Index: 1497672 (Python Code)

Max Activating Token Index: 939

Text #19

Max Range: 1.3845. Min Range: -1.3845

Max Act: 0.9382. Min Act: -0.0001

Data Index: 1447396 (Python Code)

Max Activating Token Index: 526